Research map / 3D vision / Depth and stereo
Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply the tensor low-rank prior learning network | HSI reconstruction · ICVL | PSNR: 32.610 -> 34.530 | Helped |
| apply the tensor low-rank prior learning network | HSI reconstruction · Harvard | PSNR: 31.136 -> 32.433 | Helped |
| apply the tensor low-rank prior learning network | HSI reconstruction · ICVL | SSIM: 0.966 -> 0.977 | Helped |
| apply the tensor low-rank prior learning network | HSI reconstruction · Harvard | SSIM: 0.932 -> 0.941 | Helped |
| apply the tensor low-rank prior learning network | HSI reconstruction · ICVL | SAM: 0.032 -> 0.030 | Helped |
| apply the tensor low-rank prior learning network | HSI reconstruction · Harvard | SAM: 0.078 -> 0.090 | Hurt |
| apply the tensor low-rank prior learning network | HSI reconstruction · ICVL | ERGAS: 37.531 -> 30.065 | Helped |
| apply the tensor low-rank prior learning network | HSI reconstruction · Harvard | ERGAS: 73.533 -> 62.510 | Helped |
| add residual learning when generating rank-1 tensors (ablation) | tensor low-rank prior learning network · Harvard | PSNR: 32.160 -> 32.433 | Helped |
| add residual learning when generating rank-1 tensors (ablation) | tensor low-rank prior learning network · Harvard | ERGAS: 64.370 -> 62.510 | Helped |
| use convolution learning instead of weighted summation for aggregation (ablation) | tensor low-rank prior learning network · Harvard | PSNR: 31.320 -> 32.433 | Helped |
| use convolution learning instead of weighted summation for aggregation (ablation) | tensor low-rank prior learning network · Harvard | ERGAS: 71.494 -> 62.510 | Helped |
Closest papers by meaning
- Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior (CVPR 2019 · similarity 0.91)
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.89)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · similarity 0.87)
- OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems (AAAI 2025 · similarity 0.87)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.87)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.